Machine Learning, Spring 2025
Details
Course: COMP 379-001 / COMP 479-001 Machine Learning
Level: Undergraduate and Graduate
Instructor: Daniel Moreira (dmoreira1@luc.edu)
Teaching Assistant: Kayla Salerno (ksalerno@luc.edu)
Lectures: THR, 4:15 to 6:45 PM, in person at 616 Mundelein Center
Office Hours: MON evenings and FRI mornings, 310 Doyle Center or Zoom, by appointment
Sakai: https://sakai.luc.edu/x/ZmJpr9
Overview
“Machine Learning is the field of study that gives computers the ability to learn without being explicitly programmed.”
– Arthur Samuel, 1959
Even though Samuel’s definition is now more than six decades old, it still holds true. With the recent advances in computer processing power, memory, and storage, machine learning has stressed its learn-by-example data-driven aspect, and is available — commonly as a black box — to everyone.
Annotated high-quality datasets can be easily harnessed to train a multitude of models to solve very specific problems under the different paradigms of supervised, unsupervised, hybrid (e.g., semi-supervised and self-supervised), and reinforcement learning. This course will cover these paradigms with a strong focus on supervised and unsupervised learning, trying to establish a balance between theory and practice. While students will be exposed to the theories that fight the black-box and irresponsible usage of machine learning, hands-on activities leveraging real-world data will prepare them for industrial, academic, and societal needs.
Let’s learn how the machines learn!
Requirements to attend this course are basic programming skills (especially Python), data structures, math fundamentals (such as linear algebra and calculus), and probability and statistics. This course and its materials are available in Sakai.
Tentative Schedule (materials in Sakai)
- 01/16 - Syllabus and Intro.
- 01/23 - Data-driven Aspects.
- 01/30 - Principal Component Analysis.
- 02/06 - Linear Regression.
- 02/13 - Logistic Regression.
- 02/20 - Classification Metrics.
- 02/27 - K-Nearest Neighbors, Decision Trees.
- 03/06 - Spring Break, no class.
- 03/13 - Support Vector Machines.
- 03/20 - Neural Nets.
- 03/27 - Ensemble Learning.
- 04/03 - Clustering.
- 04/10 - Convolutional Neural Nets.
- 04/17 - Easter Break, no class.
- 04/24 - Graduate Students’ Seminars.
- 05/01 - Project Presentations.
Important Dates
- 01/30 - Project groups’ definition.
- 02/07 - Assignment #1 due date.
- 02/13 - Project topics’ definition.
- 02/21 - Assignment #2 due date.
- 02/27 - Project plans’ definition and data delivery.
- 03/06 - Spring break.
- 03/13 - Midterm exam.
- 03/28 - Assignment #3 due date.
- 04/03 - Project status’ update.
- 04/11 - Assignment #4 due date.
- 04/17 - Easter break.
- 04/24 - Graduate students’ seminars.
- 04/25 - Assignment #5 due date.
- 05/01 - Project presentations and report delivery.
Notebooks (for hands-on activities)
Soon.
Grading
| Concept | Interval (%) | Concept | Interval (%) | Concept | Interval (%) | Concept | Interval (%) |
|---|---|---|---|---|---|---|---|
| A | [96, 100) | B+ | [88, 92) | C+ | [76, 80) | D+ | [64, 68) |
| A- | [92, 96) | B | [84, 88) | C | [72, 76) | D | [60, 64) |
| B- | [80, 84) | C- | [68, 72) | F | (0, 60) |
Distribution
| Undergraduate | Graduate | |
|---|---|---|
| Assignments (5) | 40% | 25% |
| Midterm Exam | 20% | 20% |
| Project | 30% | 30% |
| Seminar | N.A. | 15% |
| Participation | 10% | 10% |
| On the News | +1% (extra, max: 4%) | +1% (extra, max: 4%) |
Assignments (materials in Sakai)
Soon.
Late Policy
Deduction of 10% of the maximum possible grade for each day of delay. Works more than 9 days late will be completely lost.
Midterm Exam
- In-class written test (03/13).
Project
- Written report and presentation in the finals week, work in teams of 5 students.
- Choose and solve a problem with social impact.
- Make sure to employ a machine-learning data-driven approach.
Seminar
- Graduate students only, work in pais.
- In-class 15-min presentations plus Q&A and discussion on 04/24.
- Uncovered Machine Learning topic or scientific paper.
Possible Topics
- Semi-supervised learning.
- Self-supervised learning.
- Reinforcement learning.
- Ethics, privacy, and security in Machine Learning.
- AGI.
Participation
- Class Attendance: every presence counts.
- Today-I-missed Statements: every submission counts.
- Grace Cards: use them to pardon class absence or late work.
- Religious holidays will be honored according to the student’s faith, as stated here.
Today-I-missed Statements
After every attended class, each student will have to submit (through Sakai) a short paragraph answering one of the following:
- What is your biggest question after class? OR
- What was the most interesting point you learned today?
Inspired by Dr. Sandra Avila.
Grace Cards
Each student has three Grace Cards, which will allow them to avoid losing points because of class absence. They might also use their cards to excuse late-delivered assignments, as long as the delay is no greater than 9 days. The cards are not valid to dismiss or postpone exams, seminars (graduate students), or project-related dates. Students may use their cards at their own discretion, as long as they clearly communicate the usage to the instructor.
Life happens, be wise.
ML on the News
Posted by the students on Sakai.
Links will be added here as they are sent by the students.
Useful Links
- Machine Learning with PyTorch and Scikit-Learn book, code repository.
- Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow book, code repository,
References
- Raschka, Liu, and Mirjalili. Machine Learning with PyTorch and Scikit-Learn. Packt Book, 2022.
- Géron. Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow. O’Reilly Book, 2023.
Learning Outcomes
At the end of the course, students will master the theoretical foundations, key techniques, and applications of Machine Learning to real-world scenarios. Their repertoire will include:
- Understanding the fundamentals of Machine Learning.
- Preparing and assessing the quality of datasets for training Machine Learning algorithms.
- Developing, implementing, training, and leveraging Machine Learning algorithms.
- Assessing the performance of Machine Learning systems.
- Applying Machine Learning to real-world applications.
- Identifying the privacy and ethics issues of Machine Learning-based systems.
- Being up-to-date with emerging trends in Machine Learning.
Graduate students (within COMP 479-001), in particular, will acquire the following extra skills:
- Reading, peer-reviewing, and writing scientific papers about Machine Learning.
- Conducting research in Machine Learning, from the design of hypotheses, development of solutions, and comparison to existing baselines, to the design and execution of experiments.
Academic Integrity
Students must adhere to the LUC statements on academic integrity. These policies fully apply to this course. The penalty for task-wise academic misconduct is losing all the task’s points. Multiple events of misconduct will incur in failing the entire course (with an F grade). All cases of academic misconduct will be reported to the proper department offices. Lastly, students are not allowed to use AI assisted technology (such as ChatGPT) along the entirety of the course, unless explicitly authorized by the instructor.
Accommodations
Students who have disabilities and wish to request academic accommodations are advised to contact the Student Accessibility Center (SAC) at 773-508-3700 or sac@luc.edu as soon as possible. The SAC will provide accommodation letters that, once shared with the instructor, will be fully honored as per the terms of their content with no further questions and total confidentiality.
The SAC, student, and instructor will engage in an interactive process to determine how each student’s accommodations are applied to individual class sections. Students are welcome to visit the SAC on the first floor of Sullivan Center, Suite 117, to share questions or concern with one of their accessibility specialists.
Responsible Campus Partner
The instructor is a “Responsible Campus Partner” and will fully adhere to Loyola’s Title IX Sex-based Discrimination. He will also fully comply with the Illinois law of disclosing suspected instances of child abuse or neglect.
In addition to the instructor’s support, University’s resources are available to all the students who experience sexual/gender-based violence. Students in need are advised to safely contact the “Office for Equity & Compliance” (OEC) at equity@luc.edu or 773-508-7766. No student will ever be forced to file a report with the police.
Lastly, Loyola confidential advocates who can provide support and talk through options (medical, legal, etc.) are available at 773-494-3810. More information can be found at https://www.luc.edu/wellness.
Acknowledgements
I would like to sincerely thank Professors Sandra Avila and
Dmitriy Dligach for kindly sharing their Machine Learning course materials.
I heavily relied upon their content and experience to constitute this course.
– Daniel
Daniel Moreira
Assistant Professor of Computer Science
Computer scientist with interests in (but not limited to) Computer Vision, Machine Learning, Media Forensics, and Biometrics.